bus: mhi: host: Add mhi_power_down_keep_dev() API to support system suspend/hibernation

Currently, ath11k fails to resume from system suspend/hibernation on some
the x86 host machines with below error message:

```
ath11k_pci 0000:06:00.0: timeout while waiting for restart complete
```

This happens because, ath11k powers down the MHI stack during suspend and
that leads to destruction of the struct device associated with the MHI
channels. And during resume, ath11k calls calling mhi_sync_power_up() to
power up the MHI subsystem and that eventually calls the driver framework's
device_add() API from mhi_create_devices(). But the PM framework blocks the
struct device creation during device_add() and this leads to probe deferral
as below:

```
mhi mhi0_IPCR: Driver qcom_mhi_qrtr force probe deferral
```

The reason for deferring device creation during resume is explained in
dpm_prepare():

        /*
         * It is unsafe if probing of devices will happen during suspend or
         * hibernation and system behavior will be unpredictable in this
         * case. So, let's prohibit device's probing here and defer their
         * probes instead. The normal behavior will be restored in
         * dpm_complete().
         */

Due to the device probe deferral, qcom_mhi_qrtr_probe() API is not getting
called during resume and thus MHI channels are not prepared. So this blocks
the QMI messages from being transferred between ath11k and firmware,
resulting in a firmware initialization failure.

After consulting with Rafael, it was decided to not destroy the struct
device for the MHI channels during system suspend/hibernation because the
device is bound to appear again during resume.

So to achieve this, a new API called mhi_power_down_keep_dev() is
introduced for MHI controllers to keep the struct device when required.
This API is similar to the existing mhi_power_down() API, except that it
keeps the struct device associated with MHI channels instead of destroying
them.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20240305021320.3367-2-quic_bqiang@quicinc.com
[mani: reworded the commit message and subject]
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>

3 files changed, 56 insertions, 8 deletions

diff --git a/drivers/bus/mhi/host/internal.h b/drivers/bus/mhi/host/internal.h
index 5fe49311b8eb..aaad40a07f69 100644
--- a/drivers/bus/mhi/host/internal.h
+++ b/drivers/bus/mhi/host/internal.h
@@ -80,6 +80,7 @@ enum dev_st_transition {
 	DEV_ST_TRANSITION_FP,
 	DEV_ST_TRANSITION_SYS_ERR,
 	DEV_ST_TRANSITION_DISABLE,
+	DEV_ST_TRANSITION_DISABLE_DESTROY_DEVICE,
 	DEV_ST_TRANSITION_MAX,
 };
 
@@ -90,7 +91,8 @@ enum dev_st_transition {
 	dev_st_trans(MISSION_MODE,	"MISSION MODE")		\
 	dev_st_trans(FP,		"FLASH PROGRAMMER")	\
 	dev_st_trans(SYS_ERR,		"SYS ERROR")		\
-	dev_st_trans_end(DISABLE,	"DISABLE")
+	dev_st_trans(DISABLE,		"DISABLE")		\
+	dev_st_trans_end(DISABLE_DESTROY_DEVICE, "DISABLE (DESTROY DEVICE)")
 
 extern const char * const dev_state_tran_str[DEV_ST_TRANSITION_MAX];
 #define TO_DEV_STATE_TRANS_STR(state) (((state) >= DEV_ST_TRANSITION_MAX) ? \
diff --git a/drivers/bus/mhi/host/pm.c b/drivers/bus/mhi/host/pm.c
index 8b40d3f01acc..11c0e751f223 100644
--- a/drivers/bus/mhi/host/pm.c
+++ b/drivers/bus/mhi/host/pm.c
@@ -468,7 +468,8 @@ error_mission_mode:
 }
 
 /* Handle shutdown transitions */
-static void mhi_pm_disable_transition(struct mhi_controller *mhi_cntrl)
+static void mhi_pm_disable_transition(struct mhi_controller *mhi_cntrl,
+				      bool destroy_device)
 {
 	enum mhi_pm_state cur_state;
 	struct mhi_event *mhi_event;
@@ -530,8 +531,16 @@ skip_mhi_reset:
 	dev_dbg(dev, "Waiting for all pending threads to complete\n");
 	wake_up_all(&mhi_cntrl->state_event);
 
-	dev_dbg(dev, "Reset all active channels and remove MHI devices\n");
-	device_for_each_child(&mhi_cntrl->mhi_dev->dev, NULL, mhi_destroy_device);
+	/*
+	 * Only destroy the 'struct device' for channels if indicated by the
+	 * 'destroy_device' flag. Because, during system suspend or hibernation
+	 * state, there is no need to destroy the 'struct device' as the endpoint
+	 * device would still be physically attached to the machine.
+	 */
+	if (destroy_device) {
+		dev_dbg(dev, "Reset all active channels and remove MHI devices\n");
+		device_for_each_child(&mhi_cntrl->mhi_dev->dev, NULL, mhi_destroy_device);
+	}
 
 	mutex_lock(&mhi_cntrl->pm_mutex);
 
@@ -821,7 +830,10 @@ void mhi_pm_st_worker(struct work_struct *work)
 			mhi_pm_sys_error_transition(mhi_cntrl);
 			break;
 		case DEV_ST_TRANSITION_DISABLE:
-			mhi_pm_disable_transition(mhi_cntrl);
+			mhi_pm_disable_transition(mhi_cntrl, false);
+			break;
+		case DEV_ST_TRANSITION_DISABLE_DESTROY_DEVICE:
+			mhi_pm_disable_transition(mhi_cntrl, true);
 			break;
 		default:
 			break;
@@ -1175,7 +1187,8 @@ error_exit:
 }
 EXPORT_SYMBOL_GPL(mhi_async_power_up);
 
-void mhi_power_down(struct mhi_controller *mhi_cntrl, bool graceful)
+static void __mhi_power_down(struct mhi_controller *mhi_cntrl, bool graceful,
+			     bool destroy_device)
 {
 	enum mhi_pm_state cur_state, transition_state;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
@@ -1211,15 +1224,32 @@ void mhi_power_down(struct mhi_controller *mhi_cntrl, bool graceful)
 	write_unlock_irq(&mhi_cntrl->pm_lock);
 	mutex_unlock(&mhi_cntrl->pm_mutex);
 
-	mhi_queue_state_transition(mhi_cntrl, DEV_ST_TRANSITION_DISABLE);
+	if (destroy_device)
+		mhi_queue_state_transition(mhi_cntrl,
+					   DEV_ST_TRANSITION_DISABLE_DESTROY_DEVICE);
+	else
+		mhi_queue_state_transition(mhi_cntrl,
+					   DEV_ST_TRANSITION_DISABLE);
 
 	/* Wait for shutdown to complete */
 	flush_work(&mhi_cntrl->st_worker);
 
 	disable_irq(mhi_cntrl->irq[0]);
 }
+
+void mhi_power_down(struct mhi_controller *mhi_cntrl, bool graceful)
+{
+	__mhi_power_down(mhi_cntrl, graceful, true);
+}
 EXPORT_SYMBOL_GPL(mhi_power_down);
 
+void mhi_power_down_keep_dev(struct mhi_controller *mhi_cntrl,
+			       bool graceful)
+{
+	__mhi_power_down(mhi_cntrl, graceful, false);
+}
+EXPORT_SYMBOL_GPL(mhi_power_down_keep_dev);
+
 int mhi_sync_power_up(struct mhi_controller *mhi_cntrl)
 {
 	int ret = mhi_async_power_up(mhi_cntrl);
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 77b8c0a26674..cde01e133a1b 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -630,13 +630,29 @@ int mhi_async_power_up(struct mhi_controller *mhi_cntrl);
 int mhi_sync_power_up(struct mhi_controller *mhi_cntrl);
 
 /**
- * mhi_power_down - Start MHI power down sequence
+ * mhi_power_down - Power down the MHI device and also destroy the
+ *                  'struct device' for the channels associated with it.
+ *                  See also mhi_power_down_keep_dev() which is a variant
+ *                  of this API that keeps the 'struct device' for channels
+ *                  (useful during suspend/hibernation).
  * @mhi_cntrl: MHI controller
  * @graceful: Link is still accessible, so do a graceful shutdown process
  */
 void mhi_power_down(struct mhi_controller *mhi_cntrl, bool graceful);
 
 /**
+ * mhi_power_down_keep_dev - Power down the MHI device but keep the 'struct
+ *                           device' for the channels associated with it.
+ *                           This is a variant of 'mhi_power_down()' and
+ *                           useful in scenarios such as suspend/hibernation
+ *                           where destroying of the 'struct device' is not
+ *                           needed.
+ * @mhi_cntrl: MHI controller
+ * @graceful: Link is still accessible, so do a graceful shutdown process
+ */
+void mhi_power_down_keep_dev(struct mhi_controller *mhi_cntrl, bool graceful);
+
+/**
  * mhi_unprepare_after_power_down - Free any allocated memory after power down
  * @mhi_cntrl: MHI controller
  */